Contextualizing Argument Quality Assessment with Relevant Knowledge
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909225608806400 |
|---|---|
| author | Deshpande, Darshan Sourati, Zhivar Ilievski, Filip Morstatter, Fred |
| author_facet | Deshpande, Darshan Sourati, Zhivar Ilievski, Filip Morstatter, Fred |
| contents | Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_12280 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Contextualizing Argument Quality Assessment with Relevant Knowledge Deshpande, Darshan Sourati, Zhivar Ilievski, Filip Morstatter, Fred Computation and Language Automatic assessment of the quality of arguments has been recognized as a challenging task with significant implications for misinformation and targeted speech. While real-world arguments are tightly anchored in context, existing computational methods analyze their quality in isolation, which affects their accuracy and generalizability. We propose SPARK: a novel method for scoring argument quality based on contextualization via relevant knowledge. We devise four augmentations that leverage large language models to provide feedback, infer hidden assumptions, supply a similar-quality argument, or give a counter-argument. SPARK uses a dual-encoder Transformer architecture to enable the original argument and its augmentation to be considered jointly. Our experiments in both in-domain and zero-shot setups show that SPARK consistently outperforms existing techniques across multiple metrics. |
| title | Contextualizing Argument Quality Assessment with Relevant Knowledge |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2305.12280 |